The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read local context files such as .agents/product-marketing-context.md or .claude/product-marketing-context.md to tailor its output. While reading external data is a common surface for indirect prompt injection, this skill does not possess any dangerous capabilities (such as file-system writes, network operations, or subprocess execution) that could be exploited by malicious content within those files. The risk is effectively mitigated by the skill's restricted scope of generating text-based JSON-LD schema.
[EXTERNAL_DOWNLOADS]: The skill provides links to official, well-known validation services including the Google Rich Results Test (search.google.com) and the Schema.org Validator (validator.schema.org). These are trusted resources for the stated task of schema validation.

schema-markup